CN109785632B - Traffic flow statistical method and device - Google Patents
Traffic flow statistical method and device Download PDFInfo
- Publication number
- CN109785632B CN109785632B CN201910192624.0A CN201910192624A CN109785632B CN 109785632 B CN109785632 B CN 109785632B CN 201910192624 A CN201910192624 A CN 201910192624A CN 109785632 B CN109785632 B CN 109785632B
- Authority
- CN
- China
- Prior art keywords
- square wave
- solid
- wave signal
- data
- point cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007619 statistical method Methods 0.000 title claims abstract description 21
- 230000008859 change Effects 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 abstract description 28
- 238000004364 calculation method Methods 0.000 abstract description 4
- 239000007787 solid Substances 0.000 description 27
- 230000008569 process Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The invention provides a traffic flow statistical method and a device, wherein the method comprises the following steps: acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position; converting the point cloud data into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector; for each square wave signal, identifying a fluctuation unit included in the square wave signal according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value; and determining traffic flow data corresponding to the target position according to the number of the fluctuation units included in each square wave signal in a preset time period. The scheme can reduce the calculation resources occupied by traffic flow statistics.
Description
Technical Field
The invention relates to the technical field of traffic, in particular to a traffic flow statistical method and a traffic flow statistical device.
Background
In order to know the road traffic condition in real time, the traffic management department needs to count the traffic flow of the road, namely, the number of vehicles passing through a monitoring gate in unit time is counted, and then early warning can be carried out on the road traffic congestion condition according to the counted traffic flow.
At present, when traffic flow statistics is performed, monitoring equipment is generally installed on a corresponding road, the monitoring equipment is used for collecting image data of vehicles on the road, then the collected image data is analyzed to identify the vehicles, and then the traffic flow is determined according to the number of the identified vehicles.
Aiming at the current method for counting the traffic flow, the image data needs to be preprocessed when the image data is analyzed to identify the vehicle, then the preprocessed image data is used for identifying the vehicle, and the processes of image preprocessing and vehicle identification both need to occupy a large amount of computing resources, so that the traffic flow counting needs to occupy a large amount of computing resources, and the traffic flow counting cost is high.
Disclosure of Invention
The embodiment of the invention provides a traffic flow statistical method and a traffic flow statistical device, which can reduce the calculation resources occupied by traffic flow statistics.
In a first aspect, an embodiment of the present invention provides a traffic flow statistical method, including:
acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
converting the point cloud data into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector;
for each square wave signal, identifying a fluctuation unit included in the square wave signal according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value;
and determining traffic flow data corresponding to the target position according to the number of the fluctuation units included in each square wave signal in a preset time period.
Optionally, when the solid-state lidar sensor covers a plurality of lanes of the road to be counted, the converting the point cloud data into at least one square wave signal includes:
splitting the point cloud data into sub-point cloud data corresponding to each lane according to the position of the solid-state laser radar sensor relative to each lane;
and for each lane, converting the sub-point cloud data corresponding to the lane into the square wave signal corresponding to the lane.
Optionally, after the converting the point cloud data into at least one square wave signal, further comprising:
determining the target number of the square wave signals of which the waveforms correspond to the fluctuation units at the target time point;
and determining the number of vehicles passing through the target position at the target time point according to the target number.
Optionally, after the identifying the fluctuation unit included in the square wave signal, the method further includes:
aiming at two adjacent fluctuation units in the same square wave signal, acquiring a first distance between the two adjacent fluctuation units from the square wave signal;
calculating the interval between two vehicles corresponding to the two adjacent fluctuation units according to the first distance and angle data included in the point cloud data through a first formula;
the first formula includes:
S＝s+d·tanα-l·sinα
the point cloud data comprises a point cloud data and a point cloud data, wherein S represents the interval between two vehicles corresponding to the two adjacent fluctuation units, S represents the first distance, d represents the distance between the solid-state laser radar sensor and the road surface of the road to be counted, l represents the distance between the tail of a preceding vehicle in the two vehicles and the solid-state laser radar sensor, the point cloud data comprises angle data, and the angle data is the included angle of the connecting line between the tail of the preceding vehicle and the solid-state laser radar sensor relative to the vertical direction.
Optionally, after the identifying the fluctuation unit included in the square wave signal, the method further includes:
for each fluctuation unit, acquiring a second distance between a target vehicle corresponding to the fluctuation unit and a road reference object when the solid-state laser radar sensor performs two times of scanning from the point cloud data, and calculating the speed of the target vehicle according to a second formula as follows according to the time interval of the two times of scanning performed by the solid-state laser radar sensor;
the second formula includes:
wherein v is indicative of a vehicle speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, wherein the delta t represents the time interval of the solid-state laser radar sensor performing the two times of scanning.
In a second aspect, an embodiment of the present invention further provides a traffic flow statistics apparatus, including: the device comprises a data acquisition module, a data conversion module, a waveform identification module and a data statistics module;
the data acquisition module is used for acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
the data conversion module is used for converting the point cloud data acquired by the data acquisition module into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector;
the waveform identification module is used for identifying a fluctuation unit included in each square wave signal converted by the data conversion module according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value;
and the data statistics module is used for determining traffic flow data corresponding to the target position according to the number of the fluctuation units included in each square wave signal in a preset time period.
Optionally, when the solid-state lidar sensor covers a plurality of lanes of the road to be counted,
the data conversion module is used for splitting the point cloud data into sub-point cloud data corresponding to each lane according to the position of the solid-state laser radar sensor relative to each lane, and converting the sub-point cloud data corresponding to each lane into the square wave signal corresponding to each lane.
Alternatively,
the data statistics module is further configured to determine a target number of the square wave signals of which the waveforms correspond to the fluctuation units at a target time point, and determine the number of vehicles passing through the target position at the target time point according to the target number.
Alternatively,
the data statistics module is further configured to obtain, for two adjacent fluctuation units in the same square wave signal, a first distance between the two adjacent fluctuation units from the square wave signal, and calculate, according to the first distance and angle data included in the point cloud data, an interval between two vehicles corresponding to the two adjacent fluctuation units by using a first formula;
the first formula includes:
S＝s+d·tanα-l·sinα
the point cloud data comprises a point cloud data and a point cloud data, wherein S represents the interval between two vehicles corresponding to the two adjacent fluctuation units, S represents the first distance, d represents the distance between the solid-state laser radar sensor and the road surface of the road to be counted, l represents the distance between the tail of a preceding vehicle in the two vehicles and the solid-state laser radar sensor, the point cloud data comprises angle data, and the angle data is the included angle of the connecting line between the tail of the preceding vehicle and the solid-state laser radar sensor relative to the vertical direction.
Alternatively,
the data statistics module is further configured to acquire, for each fluctuation unit, a second distance between a target vehicle corresponding to the fluctuation unit and a road reference object when the solid-state laser radar sensor performs scanning twice, from the point cloud data, and calculate a vehicle speed of the target vehicle according to a second formula as follows according to a time interval between the solid-state laser radar sensor and the scanning twice;
the second formula includes:
wherein v is indicative of a vehicle speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, wherein the delta t represents the time interval of the solid-state laser radar sensor performing the two times of scanning.
According to the traffic flow statistical method and device provided by the embodiment of the invention, the point cloud data of the vehicle passing through the target position is collected through the solid-state laser radar sensor, then the point cloud data is converted into the square wave signal, so that the amplitude of the square wave signal corresponds to the distance data representing the distance between the solid-state laser radar sensor and the reflector, fluctuation units included in the square wave signal are identified according to the amplitude change of the square wave signal, each fluctuation unit corresponds to a movable reflector on the road to be counted, and then the traffic flow data relative to the target position can be determined according to the number of the fluctuation units included in each wave signal in a preset time period. Therefore, vehicles on a road are converted into point cloud data by using the solid laser radar sensor, the point cloud data are converted into square wave signals, then traffic flow data are determined, and the point cloud data and the square wave signals are processed by using less computing resources, so that the computing resources occupied by traffic flow statistics can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a traffic flow statistical method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a point cloud data conversion method according to an embodiment of the present invention;
FIG. 3 is a flow chart of a vehicle quantity statistical method according to an embodiment of the present invention;
FIG. 4 is a flow chart of a vehicle headway determination method provided by one embodiment of the present invention;
FIG. 5 is a flow chart of a method for determining vehicle speed provided by one embodiment of the present invention;
FIG. 6 is a schematic diagram of an apparatus for traffic flow statistics provided by an embodiment of the present invention;
fig. 7 is a schematic diagram of a traffic flow statistical apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts belong to the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a traffic flow statistical method, which may include the following steps:
step 101: acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
step 102: converting the point cloud data into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector;
step 103: for each square wave signal, identifying a fluctuation unit included in the square wave signal according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value;
step 104: and determining traffic flow data corresponding to the target position according to the number of fluctuation units included in each square wave signal in a preset time period.
According to the traffic flow statistical method provided by the embodiment of the invention, the point cloud data of the vehicle passing through the target position is collected through the solid-state laser radar sensor, then the point cloud data is converted into the square wave signal, so that the amplitude of the square wave signal corresponds to the distance data representing the distance between the solid-state laser radar sensor and the reflector, fluctuation units included in the square wave signal are identified according to the amplitude change of the square wave signal, each fluctuation unit corresponds to a movable reflector on the road to be counted, and then the traffic flow data relative to the target position can be determined according to the number of the fluctuation units included in each square wave signal in a preset time period. Therefore, vehicles on a road are converted into point cloud data by using the solid laser radar sensor, the point cloud data are converted into square wave signals, then traffic flow data are determined, and the point cloud data and the square wave signals are processed by using less computing resources, so that the computing resources occupied by traffic flow statistics can be reduced.
In the embodiment of the invention, the solid-state laser radar sensor can be arranged on a fixed bracket for installing monitoring equipment, such as a fixed bracket for installing a camera and ultrasonic speed measurement equipment, so that the existing resources can be fully utilized, and the cost for realizing the traffic flow statistical method provided by the invention is reduced. In addition, when the width of the road to be counted is small, the solid-state laser lightning sensor can be vertically and downwards arranged on the fixed support, so that the solid-state laser lightning sensor can conveniently scan the driven vehicle; when the width of the road to be counted is large, the solid laser lightning sensor can be obliquely arranged on the fixed support, the fact that the whole road can be scanned in the width direction of the road through the solid laser lightning sensor is guaranteed, and the cost of the solid laser lightning sensor is saved.
In the embodiment of the invention, after the installation and deployment of the solid-state laser lightning sensor are completed, the initial calibration is required to be carried out according to the installation height and the installation angle of the solid-state laser lightning sensor, so that the traffic flow data can be accurately determined according to the point cloud data acquired by the solid-state laser lightning sensor.
In the embodiment of the present invention, when the traffic flow data is determined according to the number of the wave units, since each wave unit corresponds to a movable reflector on the road, which may have pedestrians and non-motor vehicles in addition to motor vehicles, it is possible to determine whether the wave unit corresponds to a motor vehicle according to the span of the wave unit in the wavelength direction in the square wave signal, and then determine the traffic flow data according to the number of the remaining wave units after removing the wave unit corresponding to the non-motor vehicle, and therefore the traffic flow data should be less than or equal to the number of wave units included in each square wave signal per unit time.
Optionally, on the basis of the traffic flow statistical method shown in fig. 1, step 102 converts the point cloud data into at least one square wave signal, and when the solid-state laser lightning sensor covers multiple lanes of the road to be counted, multiple vehicles may pass through the target position from different lanes at the same time, and for this purpose, vehicles on each lane need to be identified separately. As shown in fig. 2, the specific manner of converting the point cloud data into a square wave signal may include the following steps:
step 201: dividing the point cloud data into a plurality of sub-point cloud data respectively corresponding to each lane according to the position of the solid-state laser lightning sensor relative to each lane on the road to be counted, wherein each lane corresponds to one sub-point cloud data;
step 202: and for each lane, converting the sub-point cloud data corresponding to the lane into a square wave signal corresponding to the lane.
And respectively obtaining square wave signals corresponding to each lane according to the point cloud data, and further determining the number of vehicles passing through each lane according to the square wave signals corresponding to each lane, so that the accuracy of traffic flow statistics is ensured.
In the embodiment of the invention, the solid laser lightning sensor scans according to the set direction, when a vehicle enters the scanning area of the solid laser lightning sensor, the laser emitted by the solid laser lightning sensor is shielded by the vehicle and reflected by the solid laser lightning sensor, then the solid laser lightning sensor determines the distance between the solid laser lightning sensor and a reflector according to the time difference between the emission of the laser and the reception of the reflected laser, and the determined distance is a smaller distance. When no vehicle enters a scanning area of the solid laser lightning sensor, laser emitted by the solid laser lightning sensor is reflected by a road surface to form the solid laser lightning sensor, then the solid laser lightning sensor can determine the distance between the solid laser lightning sensor and a reflector according to the time difference between the emission of the laser and the reception of the reflected laser, and the determined distance is a larger distance. The distance data determined by the solid-state laser lightning sensor are all included in the point cloud data, so that when the point cloud data are converted into square wave signals, the amplitude of the square wave signals corresponds to the distance between the solid-state laser lightning sensor and a reflector, namely, when a vehicle passes through a target position, the waveform with smaller amplitude corresponds to the waveform with smaller amplitude in the square wave signals, and when the vehicle does not pass through the target position, the waveform with larger amplitude corresponds to the waveform with larger amplitude in the square wave signals, so that whether the vehicle passes through can be identified according to the square wave signals.
It should be noted that, because the roof of the vehicle is not a regular plane shape, even if the solid-state laser lightning sensor is obliquely arranged, when a vehicle passes through a target position in parallel, the square wave signal forms two continuous concave waveforms, and the two continuous concave waveforms can be split into two independent concave waveforms according to the waveform trend. Therefore, even if there are vehicles passing the target position in parallel, the vehicles passing in parallel are identified individually based on the square wave signal.
Alternatively, on the basis of the traffic flow statistical method shown in fig. 1, after the point cloud data is converted into at least one square wave signal in step 102, the number of vehicles passing through the target position at any past time point can be determined according to each converted square wave signal. Specifically, as shown in fig. 3, the method for determining the number of vehicles passing through the target position at any target time point in the past may include the following steps:
step 301: and determining the target number of the square wave signals of which the corresponding waveforms are the fluctuation units at the target time point.
In the embodiment of the invention, the waveform corresponding to the target time point is positioned on each square wave signal, and for each square wave signal, if the waveform corresponding to the target time point on the square wave signal belongs to one fluctuation unit, the square wave signal is determined as the target square wave signal relative to the target time point. The number of target square wave signals with respect to the target time point is then determined as the target number.
Step 302: and determining the number of vehicles passing through the target position at the target time point according to the target number.
After the target number relative to the target time point is determined, the fluctuation units corresponding to the non-motor vehicles need to be removed from the fluctuation units corresponding to the target time point, and the number of the remaining fluctuation units corresponding to the target time point is the number of vehicles passing through the target position at the target time point.
Because only one vehicle can pass through each lane at the same time point, the number of vehicles passing through the target position at any time point in the past can be determined according to each square wave signal, the number of vehicles passing through the target position at each time can be further determined, and the road traffic condition can be more accurately determined according to the determined number of vehicles.
Alternatively, on the basis of the traffic flow statistical method shown in fig. 1, after the fluctuation units are identified from the square wave signals in step 103, the interval between the vehicles corresponding to the two fluctuation units can be determined according to two adjacent fluctuation units in the unified square wave signal. As shown in fig. 4, the method of determining the vehicle interval may include the steps of:
step 401: acquiring a first distance between two adjacent fluctuation units in a square wave signal aiming at the two adjacent fluctuation units in the square wave signal;
step 402: calculating the interval between the two vehicles corresponding to the two fluctuation units through a first formula according to the angle data included in the first distance and the point cloud data;
the first formula includes:
S＝s+d·tanα-l·sinα
the method comprises the following steps that S represents the interval between two vehicles corresponding to two fluctuation units, S represents a first distance, d represents the distance between a solid laser radar sensor and the road surface of a road to be counted, l represents the distance between the tail of a preceding vehicle and the solid laser radar sensor in the two vehicles included in point cloud data, and alpha represents angle data included in the point cloud data, wherein the angle data are the included angle of a connecting line between the tail of the preceding vehicle and the solid laser radar sensor relative to the vertical direction.
In the embodiment of the invention, the point cloud data not only comprises distance data representing the distance between the solid-state laser radar sensor and the reflector, but also comprises angle data representing the angle of the emitted laser or the reflected laser relative to the vertical direction. Because the laser emitted by the solid-state laser radar sensor may form a certain included angle with the vertical direction, the laser emitted by the solid-state laser radar sensor may not scan the edge part of the vehicle, but the interval between two adjacent vehicles can be determined by combining the laser reflection line according to the distance data and the angle data included in the point cloud data and the second distance acquired from the square wave signal.
Aiming at any two adjacent vehicles, after the first distance between the two fluctuation units corresponding to the two adjacent vehicles is obtained from the square wave signals, the first distance and the related distance data and angle data in the point cloud data are substituted into a first formula, so that the time interval between the two vehicles can be calculated, the accuracy of the calculation result can be ensured, and the data composition of the road traffic condition can be further enriched.
Alternatively, on the basis of the traffic flow statistical method shown in fig. 1, after the fluctuation unit is identified from the square wave signal in step 103, the vehicle speed of the vehicle corresponding to the fluctuation unit may also be determined according to the point cloud data and the square wave signal. Specifically, as shown in FIG. 5, the method of determining the vehicle speed may include the steps of:
step 501: aiming at each fluctuation unit, acquiring a second distance between a target vehicle corresponding to the fluctuation unit and a road surface reference object when the solid-state laser radar sensor performs scanning twice from the point cloud data;
step 502: calculating the speed of the target vehicle through a second formula according to the time interval and the second distance of the solid-state laser radar sensor for scanning twice;
the second formula includes:
wherein ν represents the speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, and representing the time interval of the solid-state laser radar sensor performing two times of scanning by delta t.
In the embodiment of the invention, the point cloud data acquired by the solid-state laser radar sensor comprises the distance data of the vehicle relative to the ground reference object, and the solid-state laser radar sensor can continuously emit laser for scanning, so that the vehicle speed of the vehicle can be calculated according to the distance of the same part of the vehicle relative to the ground reference object when the solid-state laser radar sensor scans twice. Therefore, the vehicle point cloud data are collected through the solid laser radar sensor, traffic flow can be counted, the speed of each passing vehicle can be detected, and the comprehensiveness of traffic monitoring is improved.
It should be noted that, the two scans of the solid-state lidar sensor corresponding to the second distance may be two scans performed continuously by the solid-state lidar sensor, or may be two non-continuous scans, that is, the solid-state lidar sensor performs one or more scans between the two scans, so that the vehicle speed may be calculated by using a larger second distance and a longer time interval, errors of the second distance and the time interval may be reduced, and accuracy of the calculated vehicle speed may be improved.
Optionally, on the basis of the traffic flow statistical method provided in the foregoing embodiments, after the traffic flow data, the vehicle interval data, and the vehicle speed data are acquired, an early warning may be performed on the road traffic condition according to the acquired data.
As shown in fig. 6 and 7, an embodiment of the present invention provides a traffic flow statistical apparatus. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware level, as shown in fig. 6, a hardware structure diagram of a device in which the traffic flow statistics apparatus provided in the embodiment of the present invention is located is shown, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 6, the device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing a packet, in general. Taking a software implementation as an example, as shown in fig. 7, as a logical apparatus, the apparatus is formed by reading, by a CPU of a device in which the apparatus is located, corresponding computer program instructions in a non-volatile memory into a memory for execution. The traffic flow statistical device provided by the embodiment comprises: a data acquisition module 701, a data conversion module 702, a waveform identification module 703 and a data statistics module 704;
the data acquisition module 701 is used for acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
the data conversion module 702 is configured to convert the point cloud data acquired by the data acquisition module 701 into at least one square wave signal, where the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to a distance between the solid-state laser radar sensor and a reflector;
a waveform identifying module 703, configured to identify, for each square wave signal converted by the data converting module 702, a fluctuation unit included in the square wave signal according to amplitude variation of the square wave signal, where the fluctuation unit is a single concave waveform with an amplitude greater than a preset amplitude threshold;
and a data statistics module 704, configured to determine traffic flow data corresponding to the target location according to the number of fluctuation units included in each square wave signal in a preset time period, where the fluctuation units are identified by the waveform identification module 703.
Alternatively, on the basis of the traffic flow statistical apparatus shown in fig. 7, when the solid-state lidar sensor covers a plurality of lanes of the road to be counted,
the data conversion module 702 is configured to split the point cloud data into sub-point cloud data corresponding to each lane according to the position of the solid-state lidar sensor relative to each lane, and convert the sub-point cloud data corresponding to each lane into a square wave signal corresponding to each lane.
Alternatively, on the basis of the traffic flow statistical apparatus shown in fig. 7,
the data statistics module 704 is further configured to determine a target number of square wave signals with waveforms of fluctuation units at the target time point, and determine a number of vehicles passing through the target position at the target time point according to the target number.
Alternatively, on the basis of the traffic flow statistical apparatus shown in fig. 7,
the data statistics module 704 is further configured to obtain, for two adjacent fluctuation units in the same square wave signal, a first distance between the two adjacent fluctuation units from the square wave signal, and calculate, according to angle data included in the first distance and point cloud data, an interval between two vehicles corresponding to the two adjacent fluctuation units through a first formula as follows;
the first formula includes:
S＝s+d·tanα-l·sinα
the method comprises the following steps that S represents the interval between two vehicles corresponding to two adjacent fluctuation units, S represents a first distance, d represents the distance between a solid laser radar sensor and the road surface of a road to be counted, l represents the distance between the tail of a preceding vehicle and the solid laser radar sensor in the two vehicles included in point cloud data, and alpha represents angle data included in the point cloud data, wherein the angle data is the included angle of a connecting line between the tail of the preceding vehicle and the solid laser radar sensor relative to the vertical direction.
Alternatively, on the basis of the traffic flow statistical apparatus shown in fig. 7,
the data statistics module 704 is further configured to, for each fluctuation unit, obtain, from the point cloud data, a second distance between the target vehicle corresponding to the fluctuation unit and the road surface reference object when the solid-state lidar sensor performs scanning twice, and calculate a vehicle speed of the target vehicle according to a second formula as follows according to a time interval between the solid-state lidar sensor and the scanning twice;
the second formula includes:
wherein ν represents the speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, and representing the time interval of the solid-state laser radar sensor performing two times of scanning by delta t.
It should be noted that, because the contents of information interaction, execution process, and the like between the units in the apparatus are based on the same concept as the method embodiment of the present invention, specific contents may refer to the description in the method embodiment of the present invention, and are not described herein again.
The embodiment of the invention also provides a readable medium, which comprises an execution instruction, and when a processor of the storage controller executes the execution instruction, the storage controller executes the traffic flow statistical method provided by each embodiment.
An embodiment of the present invention further provides a storage controller, including: a processor, a memory, and a bus;
the memory is used for storing execution instructions, the processor is connected with the memory through the bus, and when the storage controller runs, the processor executes the execution instructions stored in the memory, so that the storage controller executes the traffic flow statistical method provided by the above embodiments.
In summary, the traffic flow statistical method and apparatus provided in each embodiment of the present invention at least have the following beneficial effects:
1. in the embodiment of the invention, the point cloud data of the vehicle passing through the target position is collected through the solid-state laser radar sensor, then the point cloud data is converted into the square wave signal, the amplitude of the square wave signal corresponds to the distance data representing the distance between the solid-state laser radar sensor and the reflector, then the fluctuation units included in the square wave signal are identified according to the amplitude change of the square wave signal, each fluctuation unit corresponds to one movable reflector on the road to be counted, and then the traffic flow data relative to the target position can be determined according to the number of the fluctuation units included in each wave signal in the preset time period. Therefore, vehicles on a road are converted into point cloud data by using the solid laser radar sensor, the point cloud data are converted into square wave signals, then traffic flow data are determined, and the point cloud data and the square wave signals are processed by using less computing resources, so that the computing resources occupied by traffic flow statistics can be reduced.
2. In the embodiment of the invention, when the width of the road to be counted is smaller, the solid-state laser lightning sensor can be vertically and downwards arranged on the fixed support, so that the solid-state laser lightning sensor can conveniently scan the driven vehicle; when the width of the road to be counted is large, the solid laser lightning sensor can be obliquely arranged on the fixed support, the fact that the whole road can be scanned in the width direction of the road through the solid laser lightning sensor is guaranteed, and the cost of the solid laser lightning sensor is saved.
3. In the embodiment of the invention, the square wave signals corresponding to each lane are respectively obtained according to the point cloud data, and then the number of vehicles passing through each lane can be determined according to the square wave signals corresponding to each lane, so that the accuracy of counting the traffic flow is ensured.
4. In the embodiment of the invention, because only one vehicle can pass through each lane at the same time point, the number of vehicles passing through the target position at any time point in the past can be determined according to each square wave signal, the number of vehicles passing through the target position at each time can be further determined, and the road traffic condition can be more accurately determined according to the determined number of vehicles.
5. In the embodiment of the invention, after the first distance between the two fluctuation units corresponding to any two adjacent vehicles is obtained from the square wave signals, the first distance and the related distance data and angle data in the point cloud data are substituted into the first formula to calculate the time interval of the two vehicles, so that the accuracy of the calculation result can be ensured, and the data composition of the road traffic condition can be further enriched.
6. In the embodiment of the invention, the vehicle point cloud data is collected by the solid-state laser radar sensor, so that traffic flow can be counted, the speed of each passing vehicle can be detected, and the comprehensiveness of traffic monitoring is improved.
7. In the embodiment of the invention, the solid-state laser radar sensor has high scanning density, can be regarded as plane scanning, has extremely small scanning line interval and very small divergence at a certain distance, and has no unidentifiable condition compared with the size of a vehicle. Therefore, the vehicle can be accurately recognized even when a plurality of vehicles pass in parallel. In the two directions of the front view and the side view of the road, point cloud data acquired by the solid-state laser radar sensor can be abstracted into square wave signals. In the data processing process, the vehicle identification process is abstracted to be a square wave signal processing process with similar frequency and uncertain wavelength, and only wavelength, frequency and counting are needed, so that the computing resource requirement is low. In the top view direction, the point cloud data collected by the solid-state lidar sensor can be abstracted to be a rectangle with a certain area. In order to increase the identification accuracy, the rectangles with small areas are ignored (excluding pedestrians and non-motor vehicles) in the software processing process.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a" does not exclude the presence of other similar elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it is to be noted that: the above description is only a preferred embodiment of the present invention, and is only used to illustrate the technical solutions of the present invention, and not to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (2)
1. A traffic flow statistical method is characterized by comprising the following steps:
acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
converting the point cloud data into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector;
for each square wave signal, identifying a fluctuation unit included in the square wave signal according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value;
determining traffic flow data corresponding to the target position according to the number of the fluctuation units included in each square wave signal in a preset time period;
when the solid-state laser radar sensor covers a plurality of lanes of the road to be counted, the converting the point cloud data into at least one square wave signal comprises:
splitting the point cloud data into sub-point cloud data corresponding to each lane according to the position of the solid-state laser radar sensor relative to each lane;
for each lane, converting the sub-point cloud data corresponding to the lane into the square wave signal corresponding to the lane;
after the converting the point cloud data into at least one square wave signal, further comprising:
determining the target number of the square wave signals of which the waveforms correspond to the fluctuation units at the target time point;
determining the number of vehicles passing through the target position at the target time point according to the target number;
after the identifying the fluctuation unit included in the square wave signal, further comprising:
aiming at two adjacent fluctuation units in the same square wave signal, acquiring a first distance between the two adjacent fluctuation units from the square wave signal;
calculating the interval between two vehicles corresponding to the two adjacent fluctuation units according to the first distance and angle data included in the point cloud data through a first formula;
the first formula includes:
S＝s+d·tanα-l·sinα
the S represents the interval between two vehicles corresponding to the two adjacent fluctuation units, the S represents the first distance, the d represents the distance between the solid-state laser radar sensor and the road surface of the road to be counted, the l represents the distance between the tail of a preceding vehicle in the two vehicles and the solid-state laser radar sensor, the alpha represents the angle data, and the angle data is the included angle of a connecting line between the tail of the preceding vehicle and the solid-state laser radar sensor relative to the vertical direction;
after the identifying the fluctuation unit included in the square wave signal, further comprising:
for each fluctuation unit, acquiring a second distance between a target vehicle corresponding to the fluctuation unit and a road reference object when the solid-state laser radar sensor performs two times of scanning from the point cloud data, and calculating the speed of the target vehicle according to a second formula as follows according to the time interval of the two times of scanning performed by the solid-state laser radar sensor;
the second formula includes:
wherein v is indicative of a vehicle speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, wherein the delta t represents the time interval of the solid-state laser radar sensor performing the two times of scanning.
2. A traffic flow statistic device, characterized by comprising: the device comprises a data acquisition module, a data conversion module, a waveform identification module and a data statistics module;
the data acquisition module is used for acquiring point cloud data of vehicles passing through a target position on a road to be counted, wherein the point cloud data is acquired by a solid-state laser radar sensor arranged at the target position;
the data conversion module is used for converting the point cloud data acquired by the data acquisition module into at least one square wave signal, wherein the amplitude of the square wave signal corresponds to distance data included in the point cloud data, and the distance data corresponds to the distance between the solid-state laser radar sensor and a reflector;
the waveform identification module is used for identifying a fluctuation unit included in each square wave signal converted by the data conversion module according to the amplitude change of the square wave signal, wherein the fluctuation unit is a single concave waveform with the amplitude larger than a preset amplitude threshold value;
the data statistics module is used for determining traffic flow data corresponding to the target position according to the number of the fluctuation units included in each square wave signal in a preset time period;
when the solid-state lidar sensor covers a plurality of lanes of the road to be counted,
the data conversion module is used for splitting the point cloud data into sub-point cloud data corresponding to each lane according to the position of the solid-state laser radar sensor relative to each lane, and converting the sub-point cloud data corresponding to each lane into the square wave signal corresponding to each lane;
the data statistics module is further used for determining the target number of the square wave signals of which the waveforms correspond to the fluctuation units at the target time point, and determining the number of vehicles passing through the target position at the target time point according to the target number;
the data statistics module is further configured to obtain, for two adjacent fluctuation units in the same square wave signal, a first distance between the two adjacent fluctuation units from the square wave signal, and calculate, according to the first distance and angle data included in the point cloud data, an interval between two vehicles corresponding to the two adjacent fluctuation units by using a first formula;
the first formula includes:
S＝s+d·tanα-l·sinα
the S represents the interval between two vehicles corresponding to the two adjacent fluctuation units, the S represents the first distance, the d represents the distance between the solid-state laser radar sensor and the road surface of the road to be counted, the l represents the distance between the tail of a preceding vehicle in the two vehicles and the solid-state laser radar sensor, the alpha represents the angle data, and the angle data is the included angle of a connecting line between the tail of the preceding vehicle and the solid-state laser radar sensor relative to the vertical direction;
the data statistics module is further configured to acquire, for each fluctuation unit, a second distance between a target vehicle corresponding to the fluctuation unit and a road reference object when the solid-state laser radar sensor performs scanning twice, from the point cloud data, and calculate a vehicle speed of the target vehicle according to a second formula as follows according to a time interval between the solid-state laser radar sensor and the scanning twice;
the second formula includes:
wherein v is indicative of a vehicle speed of the target vehicle, s1And s2And respectively representing the second distance when the solid-state laser radar sensor performs two times of scanning, wherein the delta t represents the time interval of the solid-state laser radar sensor performing the two times of scanning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192624.0A CN109785632B (en) | 2019-03-14 | 2019-03-14 | Traffic flow statistical method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910192624.0A CN109785632B (en) | 2019-03-14 | 2019-03-14 | Traffic flow statistical method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109785632A CN109785632A (en) | 2019-05-21 |
| CN109785632B true CN109785632B (en) | 2021-05-04 |
Family
ID=66488009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910192624.0A Active CN109785632B (en) | 2019-03-14 | 2019-03-14 | Traffic flow statistical method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785632B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942631B (en) * | 2019-12-02 | 2020-10-27 | 北京深测科技有限公司 | Traffic signal control method based on flight time camera |
| CN110942636B (en) * | 2019-12-17 | 2021-11-26 | 南京浦和数据有限公司 | Method for realizing traffic flow statistics by multiple radar cascades |
| CN111047868B (en) * | 2020-01-17 | 2020-12-11 | 深圳市戴升智能科技有限公司 | Road vehicle flow detection method and device, computer equipment and storage medium |
| CN111540201B (en) * | 2020-04-23 | 2021-03-30 | 山东大学 | Vehicle queuing length real-time estimation method and system based on roadside laser radar |
| CN114067594B (en) * | 2020-08-05 | 2023-02-17 | 北京万集科技股份有限公司 | Method and device for planning driving path, computer equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496200A (en) * | 2011-12-12 | 2012-06-13 | 北京竞业达数码科技有限公司 | Passenger flow statistical method and passenger flow statistical device based on laser ranging |
| CN102661736A (en) * | 2012-05-17 | 2012-09-12 | 天津市星际空间地理信息工程有限公司 | Highway reorganization and expansion surveying method |
| CN205582304U (en) * | 2016-04-21 | 2016-09-14 | 武汉万集信息技术有限公司 | Channel boats and ships traffic volume survey system |
| DE102016104463A1 (en) * | 2015-03-11 | 2016-09-15 | The Boeing Company | Multidimensional merging of images in real time |
| CN106022460A (en) * | 2016-05-25 | 2016-10-12 | 重庆市勘测院 | Crowd density real-time monitoring method based on laser radar |
| CN106570454A (en) * | 2016-10-10 | 2017-04-19 | 同济大学 | Pedestrian traffic parameter extraction method based on mobile laser scanning |
| CN106846297A (en) * | 2016-12-21 | 2017-06-13 | 深圳市镭神智能系统有限公司 | Pedestrian's flow quantity detecting system and method based on laser radar |
| CN107256636A (en) * | 2017-06-29 | 2017-10-17 | 段晓辉 | A kind of traffic flow acquisition methods for merging laser scanning and video technique |
| CN107316462A (en) * | 2017-08-30 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of flow statistical method and device |
| CN108647646A (en) * | 2018-05-11 | 2018-10-12 | 北京理工大学 | The optimizing detection method and device of low obstructions based on low harness radar |
| CN108765974A (en) * | 2018-06-15 | 2018-11-06 | 江西路通科技有限公司 | A kind of traffic conditions monitoring device, monitoring method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201133413A (en) * | 2010-03-19 | 2011-10-01 | Cct Co Ltd | Detection method and system of low-speed vehicle or car-free status for a radar vehicle detector |
| JP6357737B2 (en) * | 2013-07-24 | 2018-07-18 | 富士通株式会社 | Vehicle flow measuring device, method and program |
| CN107134143A (en) * | 2016-02-26 | 2017-09-05 | 南京航空航天大学 | A kind of vehicle flowrate based on continuous wave radar sentences method for distinguishing with vehicle |
-
2019
- 2019-03-14 CN CN201910192624.0A patent/CN109785632B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496200A (en) * | 2011-12-12 | 2012-06-13 | 北京竞业达数码科技有限公司 | Passenger flow statistical method and passenger flow statistical device based on laser ranging |
| CN102661736A (en) * | 2012-05-17 | 2012-09-12 | 天津市星际空间地理信息工程有限公司 | Highway reorganization and expansion surveying method |
| DE102016104463A1 (en) * | 2015-03-11 | 2016-09-15 | The Boeing Company | Multidimensional merging of images in real time |
| CN205582304U (en) * | 2016-04-21 | 2016-09-14 | 武汉万集信息技术有限公司 | Channel boats and ships traffic volume survey system |
| CN106022460A (en) * | 2016-05-25 | 2016-10-12 | 重庆市勘测院 | Crowd density real-time monitoring method based on laser radar |
| CN106570454A (en) * | 2016-10-10 | 2017-04-19 | 同济大学 | Pedestrian traffic parameter extraction method based on mobile laser scanning |
| CN106846297A (en) * | 2016-12-21 | 2017-06-13 | 深圳市镭神智能系统有限公司 | Pedestrian's flow quantity detecting system and method based on laser radar |
| CN107256636A (en) * | 2017-06-29 | 2017-10-17 | 段晓辉 | A kind of traffic flow acquisition methods for merging laser scanning and video technique |
| CN107316462A (en) * | 2017-08-30 | 2017-11-03 | 济南浪潮高新科技投资发展有限公司 | A kind of flow statistical method and device |
| CN108647646A (en) * | 2018-05-11 | 2018-10-12 | 北京理工大学 | The optimizing detection method and device of low obstructions based on low harness radar |
| CN108765974A (en) * | 2018-06-15 | 2018-11-06 | 江西路通科技有限公司 | A kind of traffic conditions monitoring device, monitoring method and system |
Non-Patent Citations (1)
| Title |
|---|
| 用于采集交通数据的激光扫描器技术研究;张伟;《红外》;20151130;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109785632A (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109785632B (en) | Traffic flow statistical method and device | |
| CN109583280A (en) | Lane detection method, apparatus, equipment and storage medium | |
| US6792147B1 (en) | Object recognition system | |
| JP4858761B2 (en) | Collision risk determination system and warning system | |
| CN104183133A (en) | Method for acquiring and transmitting road traffic flow dynamic information | |
| JP2007257536A (en) | Road traffic monitoring device by means of millimeter-wave radar | |
| CN108828608B (en) | Laser radar background data filtering method in vehicle detection method | |
| CN113341396B (en) | Robot and charging pile identification method and device thereof | |
| CN114495512B (en) | Vehicle information detection method, system, electronic equipment and readable storage medium | |
| CN113050069A (en) | Interference signal acquisition method, device, equipment and storage medium of laser radar | |
| KR102077611B1 (en) | Laser scanner improving accuracy of detection and distance resolving power | |
| US20210364280A1 (en) | Road surface area detection device, road surface area detection system, vehicle, and road surface area detection method | |
| CN116704750B (en) | Traffic state identification method based on clustering algorithm, electronic equipment and medium | |
| CN113253299A (en) | Obstacle detection method, obstacle detection device and storage medium | |
| CN111027601B (en) | Plane detection method and device based on laser sensor | |
| CN116935631A (en) | Abnormal traffic situation detection method, device and system based on radar fusion | |
| CN116413683A (en) | Laser radar, scanning method thereof and readable storage medium | |
| CN112286178B (en) | Identification system, vehicle control system, identification method, and storage medium | |
| JP3740531B2 (en) | Parked vehicle detection method, detection system, and parked vehicle detection device | |
| CN114325678A (en) | Obstacle detection method and device and server | |
| CN114662600A (en) | Lane line detection method and device and storage medium | |
| CN114019503A (en) | FOD detection system-based airport runway foreign matter detection method, device and storage medium | |
| CN111723797B (en) | Method and system for determining bounding box of three-dimensional target | |
| CN117677862A (en) | Pseudo image point identification method, terminal equipment and computer readable storage medium | |
| CN113763308A (en) | Ground detection method, device, server and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210409 Address after: No. 1036, Shandong high tech Zone wave road, Ji'nan, Shandong Applicant after: INSPUR GROUP Co.,Ltd. Address before: 250100 First Floor of R&D Building 2877 Kehang Road, Sun Village Town, Jinan High-tech Zone, Shandong Province Applicant before: JINAN INSPUR HI-TECH INVESTMENT AND DEVELOPMENT Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |